https://github.com/anishacharya/bgmd-aistats-2022
Geometric median (GM) is a classical method in statistics for achieving a robust estimation of the uncorrupted data; under gross corruption, it achieves the optimal breakdown point of 0.5. However, its computational complexity makes it infeasible for robustifying stochastic gradient descent (SGD) for high-dimensional optimization problems. In this paper, we show that by applying Gm to only a judiciously chosen block of coordinates at a time and using a memory mechanism, one can retain the breakdown point of 0.5 for smooth non-convex problems, with non-asymptotic convergence rates comparable to the SGD with GM.
pyrddlgym-jax
JAX compilation of RDDL description files, and a differentiable planner in JAX.
delicoco-ieee-transactions
In compressed decentralized optimization settings, there are benefits to having multiple gossip steps between subsequent gradient iterations, even when the cost of doing so is appropriately accounted for e.g. by means of reducing the precision of compressed information.